© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65539
    Prev
    Next
    INDEX
    Explanations

    ings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liness
    -0.08
     Uran
    -0.08
     characterized
    -0.08
     urge
    -0.07
     invoke
    -0.07
     clôt
    -0.07
     uranium
    -0.07
    520
    -0.07
     mist
    -0.07
     зав
    -0.07
    POSITIVE LOGITS
    स्थ
    0.08
    आ
    0.08
    ̣
    0.07
    -definition
    0.07
    uced
    0.07
     표시
    0.07
    iot
    0.07
    .bold
    0.07
    emq
    0.07
    aus
    0.07
    Activations Density 0.005%

    No Known Activations